Background subtraction in inelastic scattering measurements using machine learning

R. Ghimire; A. Ratkiewicz; S. D. Pain; K. A. Chipps; J. A. Cizewski; K. L. Jones; P. Bedrossian; S. R. Carmichael; H. Garland; Claus Müller-Gatermann; R. O. Hughes; H. Jayatissa; K. Kolos; J. M. Kovoor; A. Kyle; W. Reviol; A. Richard; N. D. Scielzo; M. Siciliano; H. Sims; C. C. Ummel; M. Williams; G. L. Wilson; S. Zhu

doi:10.1016/j.nimb.2025.165649

Background subtraction in inelastic scattering measurements using machine learning

R. Ghimire, A. Ratkiewicz, S. D. Pain, K. A. Chipps, J. A. Cizewski, K. L. Jones, P. Bedrossian, S. R. Carmichael, H. Garland, Claus Müller-Gatermann, R. O. Hughes, H. Jayatissa, K. Kolos, J. M. Kovoor, A. Kyle, W. Reviol, A. Richard, N. D. Scielzo, M. Siciliano, H. SimsC. C. Ummel, M. Williams, G. L. Wilson, S. Zhu

Nuclear Structure and Nuclear Astrophysi

Research output: Contribution to journal › Article › peer-review

Abstract

Identifying, isolating, and subtracting background from the signal of interest is vital for nuclear physics experiments. These backgrounds introduce unwanted uncertainties that must be accounted for properly to extract accurate results from the signals. In nuclear reaction measurements, the typical contaminants are carbon and oxygen, contributing to background signals, and complicating the measurement of the light ejectiles. For instance, in the inelastic scattering measurement of a 20.9-MeV proton beam on ⁹⁶Mo, the ⁹⁶Mo target was contaminated with carbon and oxygen. We used random forest, a machine learning algorithm commonly used for classification and regression tasks, to separate the inelastic scattering on the carbon and oxygen contaminants from the data of interest resulting from ⁹⁶Mo(p,p^′).

Original language	English
Article number	165649
Journal	Nuclear Instruments and Methods in Physics Research, Section B: Beam Interactions with Materials and Atoms
Volume	561
DOIs	https://doi.org/10.1016/j.nimb.2025.165649
State	Published - Apr 2025

Funding

The authors express their deepest gratitude to Shaofei Zhu for his significant contributions to the successful coupling of ORRUBA with GRETINA and his subsequent collaboration. The authors also thank the dedicated staff of the Argonne Tandem Linac Accelerator System (ATLAS) at Argonne National Laboratory (ANL) for their support of this work. This work was performed under the auspices of the U.S. Department of Energy by Lawrence Livermore National Laboratory Contract No. DE-AC52-07NA27344 and supported by LDRD 22-LW-029 and LDRD 23-SI-004. This material is based upon work supported by the U.S. Department of Energy, Office of Science, Office of Nuclear Physics under Contracts No. DE-AC05-00OR22725 (ORNL), No. DE-AC02-06CH11357 (ANL), and No. DE-FG02-96-ER40963 (UTK), National Nuclear Security Administration under Contracts, USA No. DE-NA0003897 (Rutgers) and DE-NA0004066 (Rutgers), and the National Science Foundation, United States Grant No. PHY-2110985 (Rutgers). This research used resources of ANL's ATLAS facility, which is a Department of Energy Office of Science User Facility. The authors express their deepest gratitude to Shaofei Zhu for his significant contributions to the successful coupling of ORRUBA with GRETINA and his subsequent collaboration. The authors also thank the dedicated staff of the Argonne Tandem Linac Accelerator System (ATLAS) at Argonne National Laboratory (ANL) for their support of this work. This work was performed under the auspices of the US Department of Energy by Lawrence Livermore National Laboratory Contract No. DE-AC52-07NA27344 and supported by LDRD 22-LW-029 and LDRD 23-SI-004. This material is based upon work supported by the U.S. Department of Energy, Office of Science, Office of Nuclear Physics under Contracts No. DE-AC05-00OR22725 (ORNL) , No. DE-AC02-06CH11357 (ANL) , and No. DE-FG02-96-ER40963 (UTK) , National Nuclear Security Administration under Contracts No. DE-NA0003897 (Rutgers) and DE-NA0004066 (Rutgers), and the National Science Foundation Grant No. PHY-2110985 (Rutgers). This research used resources of ANL\u2019s ATLAS facility, which is a Department of Energy Office of Science User Facility.

Keywords

Background subtraction
Inelastic scattering
Machine learning
Random forest

Access to Document

10.1016/j.nimb.2025.165649

Cite this

Ghimire, R., Ratkiewicz, A., Pain, S. D., Chipps, K. A., Cizewski, J. A., Jones, K. L., Bedrossian, P., Carmichael, S. R., Garland, H., Müller-Gatermann, C., Hughes, R. O., Jayatissa, H., Kolos, K., Kovoor, J. M., Kyle, A., Reviol, W., Richard, A., Scielzo, N. D., Siciliano, M., ... Zhu, S. (2025). Background subtraction in inelastic scattering measurements using machine learning. Nuclear Instruments and Methods in Physics Research, Section B: Beam Interactions with Materials and Atoms, 561, Article 165649. https://doi.org/10.1016/j.nimb.2025.165649

@article{354defe0abbc4ca981f9634dc65a9117,

title = "Background subtraction in inelastic scattering measurements using machine learning",

abstract = "Identifying, isolating, and subtracting background from the signal of interest is vital for nuclear physics experiments. These backgrounds introduce unwanted uncertainties that must be accounted for properly to extract accurate results from the signals. In nuclear reaction measurements, the typical contaminants are carbon and oxygen, contributing to background signals, and complicating the measurement of the light ejectiles. For instance, in the inelastic scattering measurement of a 20.9-MeV proton beam on 96Mo, the 96Mo target was contaminated with carbon and oxygen. We used random forest, a machine learning algorithm commonly used for classification and regression tasks, to separate the inelastic scattering on the carbon and oxygen contaminants from the data of interest resulting from 96Mo(p,p′).",

keywords = "Background subtraction, Inelastic scattering, Machine learning, Random forest",

author = "R. Ghimire and A. Ratkiewicz and Pain, {S. D.} and Chipps, {K. A.} and Cizewski, {J. A.} and Jones, {K. L.} and P. Bedrossian and Carmichael, {S. R.} and H. Garland and Claus M{\"u}ller-Gatermann and Hughes, {R. O.} and H. Jayatissa and K. Kolos and Kovoor, {J. M.} and A. Kyle and W. Reviol and A. Richard and Scielzo, {N. D.} and M. Siciliano and H. Sims and Ummel, {C. C.} and M. Williams and Wilson, {G. L.} and S. Zhu",

note = "Publisher Copyright: {\textcopyright} 2025 Elsevier B.V.",

year = "2025",

month = apr,

doi = "10.1016/j.nimb.2025.165649",

language = "English",

volume = "561",

journal = "Nuclear Instruments and Methods in Physics Research, Section B: Beam Interactions with Materials and Atoms",

issn = "0168-583X",

publisher = "Elsevier",

}

Ghimire, R, Ratkiewicz, A, Pain, SD , Chipps, KA, Cizewski, JA, Jones, KL, Bedrossian, P, Carmichael, SR, Garland, H, Müller-Gatermann, C, Hughes, RO, Jayatissa, H, Kolos, K, Kovoor, JM, Kyle, A, Reviol, W, Richard, A, Scielzo, ND, Siciliano, M, Sims, H, Ummel, CC, Williams, M, Wilson, GL & Zhu, S 2025, 'Background subtraction in inelastic scattering measurements using machine learning', Nuclear Instruments and Methods in Physics Research, Section B: Beam Interactions with Materials and Atoms, vol. 561, 165649. https://doi.org/10.1016/j.nimb.2025.165649

TY - JOUR

T1 - Background subtraction in inelastic scattering measurements using machine learning

AU - Ghimire, R.

AU - Ratkiewicz, A.

AU - Pain, S. D.

AU - Chipps, K. A.

AU - Cizewski, J. A.

AU - Jones, K. L.

AU - Bedrossian, P.

AU - Carmichael, S. R.

AU - Garland, H.

AU - Müller-Gatermann, Claus

AU - Hughes, R. O.

AU - Jayatissa, H.

AU - Kolos, K.

AU - Kovoor, J. M.

AU - Kyle, A.

AU - Reviol, W.

AU - Richard, A.

AU - Scielzo, N. D.

AU - Siciliano, M.

AU - Sims, H.

AU - Ummel, C. C.

AU - Williams, M.

AU - Wilson, G. L.

AU - Zhu, S.

PY - 2025/4

Y1 - 2025/4

N2 - Identifying, isolating, and subtracting background from the signal of interest is vital for nuclear physics experiments. These backgrounds introduce unwanted uncertainties that must be accounted for properly to extract accurate results from the signals. In nuclear reaction measurements, the typical contaminants are carbon and oxygen, contributing to background signals, and complicating the measurement of the light ejectiles. For instance, in the inelastic scattering measurement of a 20.9-MeV proton beam on 96Mo, the 96Mo target was contaminated with carbon and oxygen. We used random forest, a machine learning algorithm commonly used for classification and regression tasks, to separate the inelastic scattering on the carbon and oxygen contaminants from the data of interest resulting from 96Mo(p,p′).

AB - Identifying, isolating, and subtracting background from the signal of interest is vital for nuclear physics experiments. These backgrounds introduce unwanted uncertainties that must be accounted for properly to extract accurate results from the signals. In nuclear reaction measurements, the typical contaminants are carbon and oxygen, contributing to background signals, and complicating the measurement of the light ejectiles. For instance, in the inelastic scattering measurement of a 20.9-MeV proton beam on 96Mo, the 96Mo target was contaminated with carbon and oxygen. We used random forest, a machine learning algorithm commonly used for classification and regression tasks, to separate the inelastic scattering on the carbon and oxygen contaminants from the data of interest resulting from 96Mo(p,p′).

KW - Background subtraction

KW - Inelastic scattering

KW - Machine learning

KW - Random forest

UR - http://www.scopus.com/inward/record.url?scp=85217744685&partnerID=8YFLogxK

U2 - 10.1016/j.nimb.2025.165649

DO - 10.1016/j.nimb.2025.165649

M3 - Article

AN - SCOPUS:85217744685

SN - 0168-583X

VL - 561

JO - Nuclear Instruments and Methods in Physics Research, Section B: Beam Interactions with Materials and Atoms

JF - Nuclear Instruments and Methods in Physics Research, Section B: Beam Interactions with Materials and Atoms

M1 - 165649

ER -

Background subtraction in inelastic scattering measurements using machine learning

Abstract

Funding

Keywords

Access to Document

Other files and links

Fingerprint

Cite this